Abstract
One of the areas with the potential to be explored in quantum computing (QC) is machine learning (ML), giving rise to quantum machine learning (QML). In an era when there is so much data, ML may benefit from either speed, complexity or smaller amounts of storage. In this work, we explore a quantum approach to a machine learning problem. Based on the work of Mari et al., we train a set of hybrid classical-quantum neural networks using transfer learning (TL). Our task was to solve the problem of classifying full-image mammograms into malignant and benign, provided by BCDR. Throughout the course of our work, heatmaps were used to highlight the parts of the mammograms that were being targeted by the networks while evaluating different performance metrics. Our work shows that this method may hold benefits regarding the generalization of complex data; however, further tests are needed. We also show that, depending on the task, some architectures perform better than others. Nonetheless, our results were superior to those reported in the state-of-the-art (accuracy of 84% against 76.9%, respectively). In addition, experiments were conducted in a real quantum device, and results were compared with the classical and simulator.

Abstract
Convolutional Neural Networks (CNN) have been successfully applied to images, text and audio, but their performance are not so good when applied to feature-based tabular data. Exceptions are works such as TabNet and DeepInsight, which employ end-to-end approaches. In this work, we propose an alternative way of using CNNs to model tabular data where knowledge is extracted from the feature space before being introduced to the network. Our strategy, Map-Optimize-Learn (MOL), changes the shape representation of samples in order to produce suitable input data for the CNN architecture. The strategy is applied to a real-world scenario of children and teenagers with cardiac pathology and compared against baseline and state of the art Machine Learning (ML) algorithms for tabular datasets. Preliminary results suggest that the strategy has potential to improve prediction quality of tabular data over end-to-end CNN methods and classical ML methods.

Abstract
This research aims to extract knowledge of sensors behavior resorting to Bayesian networks (BNs) and dynamic Bayesian networks (DBNs), a time-based BN version. These two types of models belong to the group of probabilistic graphical models (PGMs). These graphical models can be very useful to get insights from data in order to improve sensor capabilities in the industry of fire detection systems, since it can provide the conditional dependence structure among various sensor variables. Relevant sensors with fire alerts were selected and studied at device level. We conduct a data fusion analysis since we deal with heterogeneous data sources, Remote Alert (RA) with sensor states and Condition Monitoring (CM) with numerical data. To achieve an accurate fusion of the data, a pipeline was designed to align both sources of data in a regular time interval. Furthermore, a change point detection (CPD) method was used to discretize the numerical variables. In addition, one-hot encoding was used to create binarized datasets and combine all data (RA+CM). Our modeling helps understanding the dependencies among the sensor variables, highlighting that individual devices of the same type can have a very different probabilistic behavior along the time, probably due to be installed in distinct regions. Moreover, the models helped capturing strange probabilistic sensor behavior such as a low probability of a NORMAL state happening given that states FIRE, WARNING and TROUBLE did not happen. © 2022 IEEE.

Abstract
Change point detection methods try to find any sudden changes in the patterns and features of a given time series. In this paper a new change point detection method is presented, where the window width is automatically calculated. The proposed algorithm, AutoSW, is based on a Sliding Window search method of the Python ruptures package and uses a subset of statistical concepts to compute a possibly optimal window width. The proposed algorithm is compared with some other popular methods such as PELT using different real-world and synthetic time series. Results show that AutoSW can perform better than PELT producing a better set of change points in the time series tested. © 2022 IEEE.

Abstract
Since its first introduction in late 90s, the use of marketplaces has continued to grow, today virtually everything from physical assets to services can be purchased on digital marketplaces, real estate is not an exception. Some marketplaces allow acclaimed asset owners to advertise their products, to which the services gets commission/percentage from proceeds of sale/lease. Despite the success recorded in the use of the marketplaces, they are not without limitations which include identity and property fraud, impersonation and the use of centralised technology with trusted parties that are prone to single point of failures (SPOF). Being one of the most valuable assets, real estate has been a target for marketplace fraud as impersonators take pictures of properties they do not own, upload them on marketplace with promising prices that lures innocent or naive buyers. This paper addresses these issues by proposing a self sovereign identity (SSI) and smart contract based framework for identity verification and verified transaction management on secure digital marketplaces. First, the use of SSI technology enable methods for acquiring verified credential (VC) that are verifiable on a decentralised blockchain registry to identify both real estate owner(s) and real estate property. Second, the smart contracts are used to negotiate the secure transfer of real estate property deeds on the marketplace. To assess the viability of our proposal we define an application scenario and compare our work with other approaches.

Abstract
The aim of this paper is to analyse the relationship between academic inbreeding in Portugal and research collaboration, using co-authored publications as proxies. As previous research has shown that inbreeding is detrimental for research collaborations, it is hypothesised that academic inbreeding will lead to smaller research networks and, consequently, to fewer co-authored publications outside the institution of affiliation. Relying on a large data set which merged information on academics, their inbreeding status and their publications, binomial negative and fractional models were estimated to test the hypothesis. Findings show that inbred academics have smaller research networks; while they publish most co-authored papers, the relative weight of publications written in collaboration with institutional colleagues is the highest. In contrast, non-inbred academics with foreign PhDs have larger co-authorship networks. However, they publish most single-authored papers and the weight of their international co-authorships is heaviest.